Open Browser Use
🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simple.
Last verified:
What is Open Browser Use?
Open Browser Use is an open-source browser automation layer that connects local AI agents directly to your real Chrome profile. It stays neutral across agent runtimes and serves as an open-source alternative to the Chrome Browser Use capability shipped in Codex.app. The tool pairs a Chrome MV3 extension with a native host CLI binary, enabling AI agents to perform real browser automation without relying on hosted automation services.
Key features include opening and claiming tabs, running Chrome DevTools Protocol (CDP) commands, inspecting page state, watching downloads, handling file choosers, and keeping agent tabs organized. The server exposes browser tools for tab listing, opening, claiming, navigation, CDP, action plans, and cleanup. It supports standard MCP (Model Context Protocol) and can be integrated through JavaScript SDK, Python SDK, Go SDK, or the CLI.
Open Browser Use is designed for developers and teams building local AI agents who need browser automation capabilities. It targets users working with Codex, Claude Code, and other MCP clients who want platform-neutral browser control without vendor lock-in. The tool is particularly useful for B2B workflows, web scraping, data collection, and any automation task requiring authentication or persistent Chrome sessions.
The project is fully open-source under MIT license with all implementation details transparent in the GitHub repository. It includes an MCP server for agent integration, CLI for command-line usage, and SDKs for multiple programming languages.
Open Browser Use pricing
Pricing model: Freemium
Free and open-source under MIT license. The tool is completely free with no paid tiers or subscription required. All features including the CLI, SDKs (JavaScript, Python, Go), MCP server, and Chrome extension are available at no cost. Users can install via npm (npm i -g open-browser-use), Homebrew (brew tap iFurySt/open-browser-use && brew install open-browser-use), or SDKs (npm install open-browser-use-sdk, pip install open-browser-use-sdk, go get github.com/ifuryst/open-browser-use/packages/open-browser-use-go).
Open Browser Use pros
- Open-source MIT license with no vendor lock-in
- Connects to your real Chrome profile with history and cookies
- Platform-neutral across agent runtimes (Codex, Claude Code, MCP)
- Standard MCP support for easy agent integration
- No hosted automation service required - runs locally
- Multiple SDKs available: JavaScript, Python, and Go
- Chrome MV3 extension for modern browser compatibility
- Can open and claim tabs for multi-agent coordination
- Runs CDP commands for advanced browser control
- Handles file choosers and downloads automatically
- Inspects page state for dynamic content handling
- CLI makes setup and usage straightforward
- Transparent implementation - everything in public GitHub repo
- Works with existing Chrome proxy setup automatically
- Avoids headless detection since it uses real Chrome
Open Browser Use cons
- No built-in proxy management or rotation layer yet
- Requires Chrome browser installed and configured
- Needs Chrome extension installation and setup steps
- Only supports Chrome browser, not Firefox or other browsers
- Requires npm, Homebrew, or Go for installation
- No visual/no-code builder - code integration required
- Multiple components to configure (extension, native host, CLI)
- Chrome Web Store item may be temporarily unavailable requiring beta setup
Frequently asked questions about Open Browser Use
What is Open Browser Use?
Open Browser Use is an open-source browser automation layer that connects local AI agents to your real Chrome profile through an MV3 extension, native host, CLI, MCP server, and JS/Python/Go SDKs. It is platform-neutral across agent runtimes and serves as an open-source alternative to the Chrome Browser Use capability in Codex.app.
Does it support standard MCP?
Yes, Open Browser Use supports standard MCP (Model Context Protocol). It includes an MCP server plus CLI and JS/Python/Go SDKs if you want to use it outside an MCP client. It is not a custom-only framework; MCP is one of the main integration paths.
How do I install Open Browser Use?
Install the CLI via npm (npm i -g open-browser-use) on macOS, Linux, or Windows, or via Homebrew (brew tap iFurySt/open-browser-use && brew install open-browser-use). Then run 'open-browser-use setup' to register the native host and open the Chrome Web Store page to install the extension. SDKs are available via npm install open-browser-use-sdk, pip install open-browser-use-sdk, or go get github.com/ifuryst/open-browser-use/packages/open-browser-use-go.
Does it support proxy management?
Proxy management is not built in as a dedicated layer yet. Open Browser Use follows whatever proxy setup Chrome or the OS is using. For proxy rotation specifically, this feature is not currently provided as a dedicated feature.
How does tab claiming work with multiple agents?
Open Browser Use is intentionally closer to the tool/infra layer. The coordination policy is left to the upper layer, so multiple agents or callers can define how they want to claim and hand off groups/tabs, including tabs owned by another agent or a human. Users should customize the SKILL.md for their own workflow and make coordination rules explicit there.
How does it handle CDP detection?
Open Browser Use communicates through a Chrome extension plus a native host binary. There is a thin wrapper in the middle to make the surface easier and lower-friction for AI agents. The implementation details are all in the GitHub repo and everything is transparent and fully open source.
What browsers are supported?
Open Browser Use supports Google Chrome only. It uses a Chrome MV3 extension and pairs with the Chrome browser through a native host binary. Other browsers like Firefox are not supported.
Is there a paid version or subscription?
No, Open Browser Use is completely free and open-source under the MIT license. All features including the CLI, SDKs, MCP server, and Chrome extension are available at no cost with no paid tiers or subscription required.
What agents/runtimes does it work with?
Open Browser Use works with Codex, Claude Code, and any MCP client. You can install it for Codex using 'npx skills add iFurySt/open-browser-use -g -a codex --skill open-browser-use -y' and for Claude Code using 'npx skills add iFurySt/open-browser-use -g -a claude-code --skill open-browser-use -y'. It stays neutral across agent runtimes.
What if the Chrome Web Store item is unavailable?
If the Chrome Web Store item is temporarily unavailable, use 'open-browser-use setup beta' to prepare a keyed release ZIP for manual installation from chrome://extensions/. This allows you to manually install the extension when the standard setup cannot access the store.